ABSTRACT

The lack of sufficient, accurate and time series dataset on road pavement surface condition in most developing countries over time has posed a serious challenge to highway engineers in terms of developing reliable pavement management system. This study examined the trend of flexible road pavement behaviour and surface condition classification from a historic dataset using intelligent algorithms such as; Random Forest (RF), Decision Tree (DT) and Naïve Bayes (NB) theory implemented in the Waikato Environment for Knowledge Analysis (WEKA) software. Some randomly selected highway links were considered for the investigation. The surface condition attributes considered included the percentage of fatigue cracks, average rut depth and drainage condition in a relatively comprehensive database obtained from the Federal Ministry of Power, Works and Housing Nigeria. Results of the analysis revealed the performance trend and classification of road pavement surface conditions based on surface distresses. The analysis indicated that, the RF and DT algorithms yielded accurate classification against the NB algorithm which could not handle instances of missing data efficiently, hence incurred classification errors. The use of experience-based models that could handle challenges of missing data in a dataset was recommended for the development of road pavement management system using such database.